Horton

Re: LogwrtResult contended spinlock

Jaime Casanova <jcasanov@systemguards.com.ec>

View thread View on postgr.es
From: Jaime Casanova <jcasanov@systemguards.com.ec>
To: Alvaro Herrera <alvherre@2ndquadrant.com>
Cc: Andres Freund <andres@anarazel.de>, pgsql-hackers@lists.postgresql.org, Jaime Casanova <jaime.casanova@2ndquadrant.com>
Date: 2021-09-08T15:14:55Z
Lists: pgsql-hackers 
On Tue, Feb 02, 2021 at 08:19:19PM -0300, Alvaro Herrera wrote:
> Hello,
> 
> So I addressed about half of your comments in this version merely by
> fixing silly bugs.  The problem I had which I described as
> "synchronization fails" was one of those silly bugs.
> 

Hi Álvaro,

Are we waiting for another version of the patch based on Andres'
comments? Or this version is good enough for testing?

BTW, current patch still applies cleanly.

regards,

-- 
Jaime Casanova
Director de Servicios Profesionales
SystemGuards - Consultores de PostgreSQL

Commits

  1. Remove bogus assertion in pg_atomic_monotonic_advance_u64

  2. Add XLogCtl->logInsertResult

  3. Operate XLogCtl->log{Write,Flush}Result with atomics

  4. Split XLogCtl->LogwrtResult into separate struct members

  5. Introduce atomic read/write functions with full barrier semantics.

  6. Reduce the number of GetFlushRecPtr() calls done by walsenders.

  7. Remove most volatile qualifiers from xlog.c